A topic-aware graph neural network model for knowledge base updating

• URL: http://arxiv.org/abs/2208.14601v2
• Date: Thu, 1 Sep 2022 10:22:31 GMT
• Title: A topic-aware graph neural network model for knowledge base updating
• Authors: Jiajun Tong, Zhixiao Wang, Xiaobin Rui
• Abstract summary: Key challenge is to maintain an up-to-date knowledge base. Current knowledge base updating methods determine whether entities need to be updated. We construct a topic-aware graph network for knowledge updating based on the user query log.
• Score: 0.6875312133832077
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The open domain knowledge base is very important. It is usually extracted from encyclopedia websites and is widely used in knowledge retrieval systems, question answering systems, or recommendation systems. In practice, the key challenge is to maintain an up-to-date knowledge base. Different from Unwieldy fetching all of the data from the encyclopedia dumps, to enlarge the freshness of the knowledge base as big as possible while avoiding invalid fetching, the current knowledge base updating methods usually determine whether entities need to be updated by building a prediction model. However, these methods can only be defined in some specific fields and the result turns out to be obvious bias, due to the problem of data source and data structure. The users' query intentions are often diverse as to the open domain knowledge, so we construct a topic-aware graph network for knowledge updating based on the user query log. Our methods can be summarized as follow: 1. Extract entities through the user's log and select them as seeds 2. Scrape the attributes of seed entities in the encyclopedia website, and self-supervised construct the entity attribute graph for each entity. 3. Use the entity attribute graph to train the GNN entity update model to determine whether the entity needs to be synchronized. 4.Use the encyclopedia knowledge to match and update the filtered entity with the entity in the knowledge base according to the minimum edit times algorithm.

Related papers

• Towards Better Generalization in Open-Domain Question Answering by Mitigating Context Memorization [67.92796510359595]
  Open-domain Question Answering (OpenQA) aims at answering factual questions with an external large-scale knowledge corpus. It is still unclear how well an OpenQA model can transfer to completely new knowledge domains. We introduce Corpus-Invariant Tuning (CIT), a simple but effective training strategy, to mitigate the knowledge over-memorization.
  arXiv  Detail & Related papers  (2024-04-02T05:44:50Z)
• DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text [73.68051228972024]
  Large Language Models (LLMs) have exhibited impressive generation capabilities, but they suffer from hallucinations when relying on their internal knowledge. Retrieval-augmented LLMs have emerged as a potential solution to ground LLMs in external knowledge.
  arXiv  Detail & Related papers  (2023-10-31T04:37:57Z)
• Task Oriented Conversational Modelling With Subjective Knowledge [0.0]
  DSTC-11 proposes a three stage pipeline consisting of knowledge seeking turn detection, knowledge selection and response generation. We propose entity retrieval methods which result in an accurate and faster knowledge search. Preliminary results show a 4 % improvement in exact match score on knowledge selection task.
  arXiv  Detail & Related papers  (2023-03-30T20:23:49Z)
• Automatic Semantic Modeling for Structural Data Source with the Prior Knowledge from Knowledge Base [15.075047172918547]
  We propose a novel method for semantically annotating structured data sources using machine learning, graph matching and modified frequent subgraph mining. Our approach outperforms two state-of-theart solutions in tricky cases where only a few models are known.
  arXiv  Detail & Related papers  (2022-12-21T10:54:59Z)
• Leveraging Wikidata's edit history in knowledge graph refinement tasks [77.34726150561087]
  edit history represents the process in which the community reaches some kind of fuzzy and distributed consensus. We build a dataset containing the edit history of every instance from the 100 most important classes in Wikidata. We propose and evaluate two new methods to leverage this edit history information in knowledge graph embedding models for type prediction tasks.
  arXiv  Detail & Related papers  (2022-10-27T14:32:45Z)
• An Inference Approach To Question Answering Over Knowledge Graphs [7.989723691844202]
  We convert the problem of natural language querying over knowledge graphs to an inference problem over premise-hypothesis pairs. Our method achieves over 90% accuracy on MetaQA dataset, beating the existing state-of-the-art. Our approach does not require large domain-specific training data for querying on new knowledge graphs from different domains.
  arXiv  Detail & Related papers  (2021-12-21T10:07:55Z)
• Knowledge Graph Anchored Information-Extraction for Domain-Specific Insights [1.6308268213252761]
  We use a task-based approach for fulfilling specific information needs within a new domain. A pipeline constructed of state of the art NLP technologies is used to automatically extract an instance level semantic structure.
  arXiv  Detail & Related papers  (2021-04-18T19:28:10Z)
• Editing Factual Knowledge in Language Models [51.947280241185]
  We present KnowledgeEditor, a method that can be used to edit this knowledge. Besides being computationally efficient, KnowledgeEditor does not require any modifications in LM pre-training. We show KnowledgeEditor's efficacy with two popular architectures and knowledge-intensive tasks.
  arXiv  Detail & Related papers  (2021-04-16T15:24:42Z)
• Entity Context Graph: Learning Entity Representations fromSemi-Structured Textual Sources on the Web [44.92858943475407]
  We propose an approach that processes entity centric textual knowledge sources to learn entity embeddings. We show that the embeddings learned from our approach are: (i) high quality and comparable to a known knowledge graph-based embeddings and can be used to improve them further.
  arXiv  Detail & Related papers  (2021-03-29T20:52:14Z)
• Autoregressive Entity Retrieval [55.38027440347138]
  Entities are at the center of how we represent and aggregate knowledge. The ability to retrieve such entities given a query is fundamental for knowledge-intensive tasks such as entity linking and open-domain question answering. We propose GENRE, the first system that retrieves entities by generating their unique names, left to right, token-by-token in an autoregressive fashion.
  arXiv  Detail & Related papers  (2020-10-02T10:13:31Z)
• KILT: a Benchmark for Knowledge Intensive Language Tasks [102.33046195554886]
  We present a benchmark for knowledge-intensive language tasks (KILT) All tasks in KILT are grounded in the same snapshot of Wikipedia. We find that a shared dense vector index coupled with a seq2seq model is a strong baseline.
  arXiv  Detail & Related papers  (2020-09-04T15:32:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.